Reverie
Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
Open the source (opens github.com) https://github.com/knowall-ai/mcp-reverie
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: NEO4J_PASSWORD. Use a key with the least access you can.
- Marked deprecated in the MCP Registry.
What it is
MCP servers from io.github.knowall-ai.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
@knowall-ai/reverie@0.5.1
From the server's entry in the official MCP Registry
Settings it asks for
NEO4J_URIrequired · Bolt URI of the Neo4j 5 database, e.g. bolt://localhost:7687NEO4J_USERNAMErequired · Neo4j userNEO4J_PASSWORDsecret required · Neo4j passwordNEO4J_DATABASE· Database name (Enterprise only; omit on Community Edition)REVERIE_EMBEDDINGS· Embedding provider for semantic search: local (default, no API key), openai, azure, ollama, voyage or none
Related
-
Reverie
MCP serversGraph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
@knowall-ai/reverie@0.5.4 -
ReverieCache
MCP serversFree, stateless agent memory consolidation preview: keep/archive/drop diff with token estimates.
-
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
Official MCP Registry
MCP serversThe MCP project's own registry of public MCP servers, so you can look for a connector before building one.
-
MCP reference servers
MCP serversSmall example servers from the MCP project (filesystem, git, fetch, memory and more) that show how MCP works.